Skip to content

docs(skills/hindsight-docs): mirror per-provider reranker HTTP timeout env vars from #1810 #1816

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
r266-tech wants to merge 1 commit into from
Closed

docs(skills/hindsight-docs): mirror per-provider reranker HTTP timeout env vars from #1810 #1816

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions skills/hindsight-docs/references/developer/configuration.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -655,27 +655,35 @@ ZeroEntropy's `zembed-1` supports Matryoshka dimensions: `2560`, `1280`, `640`,
| `HINDSIGHT_API_RERANKER_TEI_HTTP_TIMEOUT` | HTTP request timeout for TEI reranker (seconds). Increase when using a slower CPU-based reranker under load. | `30.0` |
| `HINDSIGHT_API_RERANKER_OPENROUTER_API_KEY` | OpenRouter API key for reranking (falls back to `HINDSIGHT_API_OPENROUTER_API_KEY`, then `HINDSIGHT_API_LLM_API_KEY`) | - |
| `HINDSIGHT_API_RERANKER_OPENROUTER_MODEL` | OpenRouter rerank model | `cohere/rerank-v3.5` |
| `HINDSIGHT_API_RERANKER_OPENROUTER_TIMEOUT` | HTTP request timeout for OpenRouter reranker (seconds). | `60.0` |
| `HINDSIGHT_API_RERANKER_COHERE_API_KEY` | Cohere API key for reranking | - |
| `HINDSIGHT_API_RERANKER_COHERE_MODEL` | Cohere rerank model | `rerank-english-v3.0` |
| `HINDSIGHT_API_RERANKER_COHERE_BASE_URL` | Custom base URL for any Cohere-compatible `/rerank` endpoint (Azure AI Foundry, Jina, Voyage, self-hosted BGE, etc.). When set, the `cohere` provider bypasses the Cohere SDK and calls the endpoint directly via HTTP. | - |
| `HINDSIGHT_API_RERANKER_COHERE_TIMEOUT` | Request timeout for the Cohere reranker (seconds). Applies to both the native Cohere SDK and the Cohere-compatible HTTP path enabled by `HINDSIGHT_API_RERANKER_COHERE_BASE_URL`. | `60.0` |
| `HINDSIGHT_API_RERANKER_LITELLM_API_BASE` | LiteLLM proxy base URL for reranking | `http://localhost:4000` |
| `HINDSIGHT_API_RERANKER_LITELLM_API_KEY` | LiteLLM proxy API key for reranking (optional, depends on proxy config) | - |
| `HINDSIGHT_API_RERANKER_LITELLM_MODEL` | LiteLLM **proxy** rerank model (use provider prefix, e.g., `cohere/rerank-english-v3.0`) | `cohere/rerank-english-v3.0` |
| `HINDSIGHT_API_RERANKER_LITELLM_TIMEOUT` | HTTP request timeout for the LiteLLM proxy reranker (seconds). | `60.0` |
| `HINDSIGHT_API_RERANKER_LITELLM_SDK_API_KEY` | LiteLLM **SDK** API key for direct reranking (no proxy needed) | - |
| `HINDSIGHT_API_RERANKER_LITELLM_SDK_MODEL` | LiteLLM SDK rerank model (e.g., `deepinfra/Qwen3-reranker-8B`) | `cohere/rerank-english-v3.0` |
| `HINDSIGHT_API_RERANKER_LITELLM_SDK_API_BASE` | Custom API base URL for LiteLLM SDK (optional) | - |
| `HINDSIGHT_API_RERANKER_LITELLM_SDK_TIMEOUT` | Request timeout for the LiteLLM SDK reranker (seconds). | `60.0` |
| `HINDSIGHT_API_RERANKER_LITELLM_MAX_TOKENS_PER_DOC` | Truncate documents to this many tokens before sending to the reranker (applies to both `litellm` and `litellm-sdk`). Use for models with small context windows (e.g. set to `900` for a 1024-token limit model). Unset by default (no truncation). | - |
| `HINDSIGHT_API_RERANKER_ZEROENTROPY_API_KEY` | ZeroEntropy API key for reranking | - |
| `HINDSIGHT_API_RERANKER_ZEROENTROPY_MODEL` | ZeroEntropy rerank model (`zerank-2`, `zerank-2-small`) | `zerank-2` |
| `HINDSIGHT_API_RERANKER_ZEROENTROPY_BASE_URL` | Custom base URL for ZeroEntropy-compatible API (e.g., mock server, proxy, or self-hosted deployment) | `https://api.zeroentropy.dev` |
| `HINDSIGHT_API_RERANKER_ZEROENTROPY_TIMEOUT` | HTTP request timeout for ZeroEntropy reranker (seconds). | `60.0` |
| `HINDSIGHT_API_RERANKER_SILICONFLOW_API_KEY` | SiliconFlow API key for reranking | - |
| `HINDSIGHT_API_RERANKER_SILICONFLOW_MODEL` | SiliconFlow rerank model (e.g., `BAAI/bge-reranker-v2-m3`) | `BAAI/bge-reranker-v2-m3` |
| `HINDSIGHT_API_RERANKER_SILICONFLOW_BASE_URL` | Base URL for the SiliconFlow `/rerank` endpoint | `https://api.siliconflow.cn/v1` |
| `HINDSIGHT_API_RERANKER_SILICONFLOW_TIMEOUT` | HTTP request timeout for SiliconFlow reranker (seconds). | `60.0` |
| `HINDSIGHT_API_RERANKER_ALIBABA_API_KEY` | Alibaba Cloud DashScope API key for reranking | - |
| `HINDSIGHT_API_RERANKER_ALIBABA_MODEL` | DashScope rerank model | `qwen3-rerank` |
| `HINDSIGHT_API_RERANKER_ALIBABA_TIMEOUT` | HTTP request timeout for the Alibaba Cloud DashScope reranker (seconds). | `60.0` |
| `HINDSIGHT_API_RERANKER_GOOGLE_PROJECT_ID` | Google Cloud project ID for Discovery Engine reranking (falls back to `HINDSIGHT_API_LLM_VERTEXAI_PROJECT_ID`) | - |
| `HINDSIGHT_API_RERANKER_GOOGLE_MODEL` | Google Discovery Engine ranking model | `semantic-ranker-default-004` |
| `HINDSIGHT_API_RERANKER_GOOGLE_SERVICE_ACCOUNT_KEY` | Path to service account JSON key (falls back to `HINDSIGHT_API_LLM_VERTEXAI_SERVICE_ACCOUNT_KEY`). If unset, uses ADC. | - |
| `HINDSIGHT_API_RERANKER_GOOGLE_TIMEOUT` | HTTP request timeout for Google Discovery Engine reranker (seconds). | `60.0` |
| `HINDSIGHT_API_RERANKER_FLASHRANK_MODEL` | FlashRank model for fast CPU-based reranking | `ms-marco-MiniLM-L-12-v2` |
| `HINDSIGHT_API_RERANKER_FLASHRANK_CACHE_DIR` | Cache directory for FlashRank models | System default |
| `HINDSIGHT_API_RERANKER_FLASHRANK_CPU_MEM_ARENA` | Enable ONNX Runtime CPU memory arena for FlashRank. When `true`, ONNX pre-allocates a memory arena that never shrinks, causing RSS to grow monotonically. `false` trades slightly slower per-call allocation for bounded RSS. | `false` |
Expand Down
Loading